restructure README.md to follow python layout - #2
Merged
Merged
Conversation
qmuntal
reviewed
Oct 27, 2025
qmuntal
left a comment
qmuntal
left a comment
Member
There was a problem hiding this comment.
Most of the samples won't work, but it's better than before :)
qmuntal
added a commit
that referenced
this pull request
Dec 10, 2025
restructure README.md to follow python layout
qmuntal
added a commit
that referenced
this pull request
Dec 10, 2025
restructure README.md to follow python layout
qmuntal
added a commit
that referenced
this pull request
Dec 10, 2025
restructure README.md to follow python layout
github-actions Bot
added a commit
that referenced
this pull request
May 25, 2026
Fix two bugs that prevent parallel tool calls from rendering correctly in AG-UI protocol clients: Bug #2: Make ToolCallResultEvent.MessageId deterministically unique using result-{callId} format. Multiple tool results in the same update batch previously shared a single generated message ID, collapsing them in FE reconciliation. Bug #3: Coalesce consecutive assistant-with-tool-calls messages in toAgentMessages. The AG-UI client creates one assistant message per tool call when parentMessageId is absent. Sending them as separate messages to the LLM triggers HTTP 400 because OpenAI requires tool results to immediately follow every tool_call_id in an assistant message. Also removes the now-dead hasFunctionResultContent helper. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
gdams
pushed a commit
that referenced
this pull request
May 26, 2026
Fix two bugs that prevent parallel tool calls from rendering correctly in AG-UI protocol clients: Bug #2: Make ToolCallResultEvent.MessageId deterministically unique using result-{callId} format. Multiple tool results in the same update batch previously shared a single generated message ID, collapsing them in FE reconciliation. Bug #3: Coalesce consecutive assistant-with-tool-calls messages in toAgentMessages. The AG-UI client creates one assistant message per tool call when parentMessageId is absent. Sending them as separate messages to the LLM triggers HTTP 400 because OpenAI requires tool results to immediately follow every tool_call_id in an assistant message. Also removes the now-dead hasFunctionResultContent helper. Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I think Copilot might have hallucinated about some of the implementation but I'll let @qmuntal confirm